Instructions to use TinyLlama/TinyLlama-1.1B-python-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TinyLlama/TinyLlama-1.1B-python-v0.1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-python-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-python-v0.1")
model = AutoModelForMultimodalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-python-v0.1")

llama-cpp-python

How to use TinyLlama/TinyLlama-1.1B-python-v0.1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TinyLlama/TinyLlama-1.1B-python-v0.1",
	filename="ggml-model-q4_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TinyLlama/TinyLlama-1.1B-python-v0.1 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0
# Run inference directly in the terminal:
llama cli -hf TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0
# Run inference directly in the terminal:
llama cli -hf TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0

Use Docker

docker model run hf.co/TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0

LM Studio
Jan

vLLM

How to use TinyLlama/TinyLlama-1.1B-python-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TinyLlama/TinyLlama-1.1B-python-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TinyLlama/TinyLlama-1.1B-python-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0

SGLang

How to use TinyLlama/TinyLlama-1.1B-python-v0.1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "TinyLlama/TinyLlama-1.1B-python-v0.1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TinyLlama/TinyLlama-1.1B-python-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "TinyLlama/TinyLlama-1.1B-python-v0.1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TinyLlama/TinyLlama-1.1B-python-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use TinyLlama/TinyLlama-1.1B-python-v0.1 with Ollama:
```
ollama run hf.co/TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0
```

Unsloth Studio

How to use TinyLlama/TinyLlama-1.1B-python-v0.1 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TinyLlama/TinyLlama-1.1B-python-v0.1 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TinyLlama/TinyLlama-1.1B-python-v0.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TinyLlama/TinyLlama-1.1B-python-v0.1 to start chatting

Atomic Chat new
Docker Model Runner
How to use TinyLlama/TinyLlama-1.1B-python-v0.1 with Docker Model Runner:
```
docker model run hf.co/TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0
```

Lemonade

How to use TinyLlama/TinyLlama-1.1B-python-v0.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TinyLlama/TinyLlama-1.1B-python-v0.1:Q4_0

Run and chat with the model

lemonade run user.TinyLlama-1.1B-python-v0.1-Q4_0

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

TinyLlama-1.1B

https://github.com/jzhang38/TinyLlama

The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.

We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.

This Model

This is a code LM finetuned(or so-called continue pretrianed) from the 500B TinyLlama checkpoint with another 7B Python data from the starcoderdata.

While the finetuning data is exclusively Python, the model retains its ability in many other languages such as C or Java.

The HumanEval accuracy is 14.

It can be used as the draft model to speculative-decode larger models such as models in the CodeLlama family.

Downloads last month: 1,722

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for TinyLlama/TinyLlama-1.1B-python-v0.1

Adapters

3 models

Quantizations

3 models

TinyLlama
/

TinyLlama-1.1B-python-v0.1

TinyLlama-1.1B

This Model

Model tree for TinyLlama/TinyLlama-1.1B-python-v0.1

Dataset used to train TinyLlama/TinyLlama-1.1B-python-v0.1

Space using TinyLlama/TinyLlama-1.1B-python-v0.1 1